We study a collaborative scenario where a user not only instructs a system to complete tasks, but also acts alongside it. This allows the user to adapt to the system abilities by changing their language or deciding to simply accomplish some tasks themselves, and requires the system to effectively recover from errors as the user strategically assigns it new goals. We build a game environment to study this scenario, and learn to map user instructions to system actions. We introduce a learning approach focused on recovery from cascading errors between instructions, and modeling methods to explicitly reason about instructions with multiple goals. We evaluate with a new evaluation protocol using recorded interactions and online games with human users, and observe how users adapt to the system abilities.

Meta reinforcement learning (meta-RL) is able to accelerate the acquisition of new tasks by learning from past experience. Current meta-RL methods usually learn to adapt to new tasks by directly optimizing the parameters of policies over primitive actions. However, for complex tasks which requires sophisticated control strategies, it would be quite inefficient to to directly learn such a meta-policy. Moreover, this problem can become more severe and even fail in spare reward settings, which is quite common in practice. To this end, we propose a new meta-RL algorithm called meta goal-generation for hierarchical RL (MGHRL) by leveraging hierarchical actor-critic framework. Instead of directly generate policies over primitive actions for new tasks, MGHRL learns to generate high-level meta strategies over subgoals given past experience and leaves the rest of how to achieve subgoals as independent RL subtasks. Our empirical results on several challenging simulated robotics environments show that our method enables more efficient and effective meta-learning from past experience and outperforms state-of-the-art meta-RL and Hierarchical-RL methods in sparse reward settings.

Namboodiri Indian Institute of Technology, Kanpur { badri,sandepkr,vinodkk,vinaypn} @iitk.ac.in Abstract Generating natural questions from an image is a semantic task that requires using visual and language modality to learn multimodal representations. Images can have multiple visual and language contexts that are relevant for generating questions namely places, captions, and tags. In this paper, we propose the use of exemplars for obtaining the relevant context. We obtain this by using a Multimodal Differential Network to produce natural and engaging questions. The generated questions show a remarkable similarity to the natural questions as validated by a human study. Further, we observe that the proposed approach substantially improves over state-of-the-art benchmarks on the quantitative metrics (BLEU, METEOR, ROUGE, and CIDEr). 1 Introduction To understand the progress towards multimedia vision and language understanding, a visual Turing test was proposed by (Geman et al., 2015) that was aimed at visual question answering (Antol et al., 2015). Visual Dialog (Das et al., 2017) is a natural extension for VQA. Current dialog systems as evaluated in (Chattopadhyay et al., 2017) show that when trained between bots, AIAI dialog systems show improvement, but that does not translate to actual improvement for Human-AI dialog. This is because, the questions generated by bots are not natural (humanlike) and therefore does not translate to improved human dialog. Therefore it is imperative that improvement in the quality of questions will enable dialog agents to perform well in human interactions. Further, (Ganju et al., 2017) show that unanswered questions can be used for improving VQA, Image captioning and Object Classification. An interesting line of work in this respect is the work of (Mostafazadeh et al., 2016). Here the authors have proposed the challenging task of generating natural questions for an image. One aspect that is central to a question is the context that is relevant to generate it. As can be seen in Figure 1, an image with a person on a skateboard would result in questions related to the event.

Analyst Forrester defines robotic process automation (RPA) as a technology that provisions software agents – bots – that can mimic human interactions with software systems. These bots run predictable tasks, and act either in concert with humans (attended RPA) or mostly autonomously (unattended RPA). Increasingly, RPA is adding artificial intelligence (AI)-based capabilities, such as reading unstructured data. IT research firm Computer Economics says in its April 2019 Technology trends report that bots are typically taught by human example to respond to various triggers. For example, when an employee submits a change of address form to the human resources (HR) department, the bot could then be used to trigger an update to the records in payroll, benefits systems, expense reporting and accounts payable, just as a human clerical worker might do.

The field of artificial intelligence (AI) started in the 1950's in the defense industry, and has evolved over the years. In the 2010s, new computer-based "deep-learning" methods were introduced that significantly accelerated the field. Physician-scientists are using this technology in the medical field to improve diagnostic methods. One such researcher is PCF-funded investigator Dr. Beatrice Knudsen, a Professor of Biomedical Sciences and Pathology and Director of Translational Pathology at Cedars-Sinai Medical Center in Los Angeles. She is one of the world's leading research pathologists, and is an expert on diagnosis of prostate cancer and other diseases from tissue specimens.

Former Managing Director and Head of Investment Banking in South East Asia for Morgan Stanley (opened their investment banking office in Singapore in 1992). Head of Investment Banking in Asia/Japan and Member of Global Investment Banking Management Committee for Deutsche Bank (formerly called Deutsche Morgan Grenfell) in 1995.

If you've heard of quantum computing, you might be excited about the possibility of applying it to machine learning applications. I work at Springboard, and we recently launched a machine learning bootcamp that includes a job guarantee. We want to make sure our graduates are exposed to cutting-edge machine learning applications -- so we put together this article as part of our research into the intersection of quantum computing and machine learning. Let's start by examining the difference between quantum computing and classical computing. In classical computing, your data is stored in physical bits and it is binary and mutually exhaustive: a bit is either in a 0 state or in a 1 state and it cannot be both at the same time.

In a recent Cray-sponsored survey, over 70% of respondents say Artificial Intelligence will be critical to their business by 2022, but cite a "lack of skilled resources" as a major challenge. In order to address those resource constraints, Cray, a Hewlett Packard Enterprise company has partnered with Stradigi AI, a leading Artificial Intelligence solution provider, to provide the skilled resources organizations need to be successful with AI. We'll have AI experts from Cray and Stradigi AI on hand to explain our proven methodology for guiding AI implementations from pilot to production.

Please join us this evening, October 29th, to discuss interpretable machine learning and the techniques that go behind making a white-box model! Machine learning systems are used today to make life-altering decisions about employment, bail, parole, and lending. Moreover, the scope of decisions delegated to machine learning systems seems likely only to expand in the future. Unfortunately, serious discrimination, privacy, and even accuracy concerns can be raised about these systems. Many researchers and practitioners are tackling disparate impact, inaccuracy, privacy violations, and security vulnerabilities with a number of brilliant, but often siloed, approaches.